diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 7e890065cf39..19f2f9498b27 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -105,6 +105,82 @@ static int store_updates_sp(struct pt_regs *regs) } return 0; } +/* + * do_page_fault error handling helpers + */ + +#define MM_FAULT_RETURN 0 +#define MM_FAULT_CONTINUE -1 +#define MM_FAULT_ERR(sig) (sig) + +static int out_of_memory(struct pt_regs *regs) +{ + /* + * We ran out of memory, or some other thing happened to us that made + * us unable to handle the page fault gracefully. + */ + up_read(¤t->mm->mmap_sem); + if (!user_mode(regs)) + return MM_FAULT_ERR(SIGKILL); + pagefault_out_of_memory(); + return MM_FAULT_RETURN; +} + +static int do_sigbus(struct pt_regs *regs, unsigned long address) +{ + siginfo_t info; + + up_read(¤t->mm->mmap_sem); + + if (user_mode(regs)) { + info.si_signo = SIGBUS; + info.si_errno = 0; + info.si_code = BUS_ADRERR; + info.si_addr = (void __user *)address; + force_sig_info(SIGBUS, &info, current); + return MM_FAULT_RETURN; + } + return MM_FAULT_ERR(SIGBUS); +} + +static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) +{ + /* + * Pagefault was interrupted by SIGKILL. We have no reason to + * continue the pagefault. + */ + if (fatal_signal_pending(current)) { + /* + * If we have retry set, the mmap semaphore will have + * alrady been released in __lock_page_or_retry(). Else + * we release it now. + */ + if (!(fault & VM_FAULT_RETRY)) + up_read(¤t->mm->mmap_sem); + /* Coming from kernel, we need to deal with uaccess fixups */ + if (user_mode(regs)) + return MM_FAULT_RETURN; + return MM_FAULT_ERR(SIGKILL); + } + + /* No fault: be happy */ + if (!(fault & VM_FAULT_ERROR)) + return MM_FAULT_CONTINUE; + + /* Out of memory */ + if (fault & VM_FAULT_OOM) + return out_of_memory(regs); + + /* Bus error. x86 handles HWPOISON here, we'll add this if/when + * we support the feature in HW + */ + if (fault & VM_FAULT_SIGBUS) + return do_sigbus(regs, addr); + + /* We don't understand the fault code, this is fatal */ + BUG(); + return MM_FAULT_CONTINUE; +} /* * For 600- and 800-family processors, the error_code parameter is DSISR @@ -124,11 +200,12 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, { struct vm_area_struct * vma; struct mm_struct *mm = current->mm; - siginfo_t info; + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; int code = SEGV_MAPERR; - int is_write = 0, ret; + int is_write = 0; int trap = TRAP(regs); int is_exec = trap == 0x400; + int fault; #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) /* @@ -145,6 +222,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, is_write = error_code & ESR_DST; #endif /* CONFIG_4xx || CONFIG_BOOKE */ + if (is_write) + flags |= FAULT_FLAG_WRITE; + #ifdef CONFIG_PPC_ICSWX /* * we need to do this early because this "data storage @@ -152,13 +232,11 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, * look at it */ if (error_code & ICSWX_DSI_UCT) { - int ret; - - ret = acop_handle_fault(regs, address, error_code); - if (ret) - return ret; + int rc = acop_handle_fault(regs, address, error_code); + if (rc) + return rc; } -#endif +#endif /* CONFIG_PPC_ICSWX */ if (notify_page_fault(regs)) return 0; @@ -216,6 +294,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, if (!user_mode(regs) && !search_exception_tables(regs->nip)) goto bad_area_nosemaphore; +retry: down_read(&mm->mmap_sem); } else { /* @@ -338,30 +417,43 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - ret = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0); - if (unlikely(ret & VM_FAULT_ERROR)) { - if (ret & VM_FAULT_OOM) - goto out_of_memory; - else if (ret & VM_FAULT_SIGBUS) - goto do_sigbus; - BUG(); + fault = handle_mm_fault(mm, vma, address, flags); + if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + int rc = mm_fault_error(regs, address, fault); + if (rc >= MM_FAULT_RETURN) + return rc; } - if (ret & VM_FAULT_MAJOR) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); + + /* + * Major/minor page fault accounting is only done on the + * initial attempt. If we go through a retry, it is extremely + * likely that the page will be found in page cache at that point. + */ + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) { + current->maj_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, + regs, address); #ifdef CONFIG_PPC_SMLPAR - if (firmware_has_feature(FW_FEATURE_CMO)) { - preempt_disable(); - get_lppaca()->page_ins += (1 << PAGE_FACTOR); - preempt_enable(); + if (firmware_has_feature(FW_FEATURE_CMO)) { + preempt_disable(); + get_lppaca()->page_ins += (1 << PAGE_FACTOR); + preempt_enable(); + } +#endif /* CONFIG_PPC_SMLPAR */ + } else { + current->min_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, + regs, address); + } + if (fault & VM_FAULT_RETRY) { + /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk + * of starvation. */ + flags &= ~FAULT_FLAG_ALLOW_RETRY; + goto retry; } -#endif - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); } + up_read(&mm->mmap_sem); return 0; @@ -382,28 +474,6 @@ bad_area_nosemaphore: return SIGSEGV; -/* - * We ran out of memory, or some other thing happened to us that made - * us unable to handle the page fault gracefully. - */ -out_of_memory: - up_read(&mm->mmap_sem); - if (!user_mode(regs)) - return SIGKILL; - pagefault_out_of_memory(); - return 0; - -do_sigbus: - up_read(&mm->mmap_sem); - if (user_mode(regs)) { - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = BUS_ADRERR; - info.si_addr = (void __user *)address; - force_sig_info(SIGBUS, &info, current); - return 0; - } - return SIGBUS; } /*